DOCSLIB.ORG

Pattern Classification and Analysis of Memory Processing in Depression

Total Page：16

File Type：pdf, Size：1020Kb

Download full-text PDF Read full-text
Pattern Classification and Analysis of Memory Processing in Depression Pattern Classification and Analysis of Memory Processing in Depression Using EEG Signals Kin Ming Puk1, Kellen C. Gandy2, Shouyi Wang1, and Heekyeong Park2 1 Department of Industrial, Manufacturing, & Systems Engineering 2 Department of Psychology University of Texas at Arlington 701 S Nedderman Dr, Arlington, TX 76019 {[email protected],[email protected], [email protected],[email protected]} Abstract. An automatic, electroencephalogram (EEG) based approach of diagnosing de- pression with regard to memory processing is presented. EEG signals are extracted from 15 depressed subjects and 12 normal subjects during experimental tasks of reorder and re- hearsal [2]. After preprocessing noisy EEG signals, nine groups of mathematical features are extracted and classification with support vector machine (SVM) is conducted under a five-fold cross-validation, with accuracy of up to 70% - 100%. The contribution of this paper lies in the analysis and visualization of the difference between depressed and control subjects in EEG signals. Keywords: depression, working memory, long-term memory, EEG, machine learning, sig- nal processing, feature extraction, feature selection, classification, support vector machine 1 Introduction Depression, according to [3], is a term referring to a disabling and prevalent psychiatric illness, major depressive disorder (also known as clinical depression). Depressed patients tend to feel sad and pessimistic for a long period of time, and they are likely associated with low self-esteem and tendency to commit suicide, among other negative symptoms. It has been reported that depressed patients suffer from poor concentration and memory. For the sake of evaluating the effectiveness of memory retrieval, working memory (WM) and long-term memory (LTM) are the primary research interest in this work [7]. Techniques of brain signal analysis of EEG with classification framework in data mining is adopted in this regard. Indeed computer-aided diagnosis using EEG signals is a popular field of research. Classification framework consists of EEG preprocessing, feature extraction, feature selection and classifier. Depending on the disorder/disease and framework, classification accuracy may vary from 80% [4] to 97% [6]. Interested readers are referred to [4], [5], [6], [11], [12] for more details. 2 Experimental Design and Data Acquisition Participant Participants were recruited from the University of Texas at Arlington. Each partic- ipant completed a pre-screen questionnaire which included the Center of Epidemiological Studies Depression Scale (CES-D) for separating groups of individuals with high and low depressive symp- tomatology. Individuals who scored 25 or above qualified to be part of the high group, below 15 to be part of the low group, and 15-25 to be part of the moderate group. A total of 60 individuals - 20 with low depression, 20 with moderate depression, and 20 with high depression - were recruited for the purposes of this experiment. In this EEG analysis, only data from 15 high depression indi- viduals (4 males, 11 females; Age: 20.3 ± 3.21) and low depression individuals (4 males, 8 females; Age: 20.5 ± 2.66) is used due to cleanliness of data and for the sake of binary classification (so that data from moderately depressed subjects is not used). Procedure Tasks of varying cognitive difficulty in semantic processing are designed with reference to [2]. During the entire experimental procedure, EEG signal is measured using the Brain Vision 32 channel system and recorded using the Pycorder software. 2 Puk, Gandy, Wang and Park The assessment of working memory ("WM procedure") consists of "reorder" and rehearsal". For reorder tasks, participants are instructed to mentally reorder the sequence of three pictorial items based on their physical weight in an arrangement from lightest to heaviest, with 1 repre- senting the lightest item, 2 representing the mid-weight item, and 3 representing the heaviest item ("reorder"). For rehearsal tasks, participants were instructed to remember the sequence of three pictorial items based on their serial order from top to bottom, with 1 representing the top item, 2 representing the middle item, and 3 representing the bottom item ("rehearsal"). On the other hand, long-term memory is assessed by differentiating "new" from old images ("LTM procedure"). After the WM procedure, participants are asked to continue with LTM pro- cedure by indicating whether each image appears using their right hand ("new"), followed by a confidence rating of that decision which ranged from 1 to 3, with 1 representing low confidence, 2 representing medium confidence, and 3 representing high confidence using their left hand. 3 Extraction and Classification of EEG Features Preprocessing of EEG Signals EEG data of 32 electrodes (FP1, FP2, F7, F3, Fz, F4, F8, FT9, FC5, FC1, FC2, FC6, FT10, T9, T7, C3, Cz, C4, T8, T10, CP5, CP1, CP2, CP6, P7, P3, Pz, P4, P8, Oz, Oz, O2; see Fig. 2) are imported into Matlab with software package "EEGLAB" [8]. EEG signals will then be re-referenced at channels T9 and T10 since these two channels are least influenced by cognitive processing, resampled from 1000 Hz to 256 Hz for reducing data size, and bandpass filtered at 1-35 Hz for removing unnecessary signal noise. Fig. 1: i) WM, Top: On rehearsal trials, participants are instructed to maintain the serial order of the three presented items (top to bottom), whereas on reorder trials, participants were instructed to mentally rearrange the items according to their physical weight (lightest to heaviest). ii) LTM, Bottom: Participants are instructed to recognize whether the image appeared in WM procedure or not. Epoching After preprocessing, EEG signal is partitioned into different epoches according to the experiment procedure for working memory and long-term memory. Each participant were shown 504 images, which correspond to 504 trials. For working memory (Fig. 1), each trial (either reorder or rehearsal) consists of a cue on the center of the screen (A1, 500 ms), inter-stimulus interval (A2, 1000 ms), showing of the stimuli (A3, 2000 ms), delay (A4, 4000 ms) and probing for the answer (A5, 2000 ms). Therefore, EEG Pattern Classification of Memory Processing in Depression 3 signal of 336 trials, with each trial lasting for 10500 ms (including baseline of 1000 ms before the start of each trial) are extracted for working memory. As for long-term memory (Fig. 1), the procedure consists of item recognition (B1, 2000 ms) and rating the confidence of the recognition (B2, 1500 ms). Therefore, EEG signal of 168 trials, with each trial lasting for 4500 ms (including baseline of 1000 ms before the start of each trial) are extracted for long-term memory. Please note that baseline removal can only be done after epoching with the availability of baseline signal. Artifact Removal Artifact is then removed from EEG signal with EEGLAB plugin - ADJUST (An Automatic EEG artifact Detector based on the Joint Use of Spatial and Temporal features) [10]. Artifact features including eye blinks, (vertical and horizontal) eye movements and generic discontinuities are accounted for. The four stages are i) Epoched EEG signal is first decomposed into different independent components using independent component analysis (ICA); ii) artifact features for each component are computed; iii) the value of each artifact feature for each component is to be checked against threshold value computed by Expectation-Maximization [23] in order to determine whether that component is an artifact; and iv) EEG signal is reconstructed using independent components which are not rejected. Feature Extraction Nine groups of mathematical features - statistical features, time-frequency features, signal power, Hjorth parameters, Hurst exponent, band power asymmetry and spectral edge frequency - are extracted from each trial of subjects as in [4], [6] and [11]. These nine groups of features are extracted from EEG signal at each of the 30 channels (2 channels removed after rereferencing). They are then concatenated as a feature vector. This procedure is applied to all trials of EEG data for all participants. In the following, X = fx1; x2; :::; xmg denote a single- channel signal with m time points. 1) Statistical Features: Mean, variance, skewness, kurtosis at theta, alpha, beta and low gamma bands are computed. More specifically, mean is the averaged signal amplitude, variance measures the signal variability to the mean, skewness quantifies the extent to which the distribution leans to one side of the mean, and kurtosis measures the 'peakedness' of the distribution. 2) Morphological features: Three morphological features at theta, alpha, beta and low gamma bands were extracted to describe morphological characteristics of a single-channel signal as in [24] and [25]. • Curve length is the sum of distances between any two pair of consecutive points. Intuition behind this feature is that curve length increase with the signal magnitude, frequency and amplitude variation. It is mathematically calculated as follows: m−1 1 X jx − x j (1) m − 1 i+1 i i=1 • Number of peaks measures the overall frequency of a signal. It is mathematically calculated as follows: m−2 1 X max(0; sgn(x − x ) − sgn(x − x )) (2) 2 i+2 i+1 i+1 i i=1 • Average nonlinear energy, according to [26], is sensitive to spectral changes and is calculated as: m−1 1 X x2 − x x (3) m − 2 i i−1 i+1 i=2 3) Time-Frequency Features: Wavelet transform (WT) is a powerful tool to perform time- frequency analysis of signals. The fundamental idea of WT is to represent a signal by a linear combination of a set of functions obtained by shifting or dilating a particular function called mother wavelet [13]. The WT of a signal X(t) is defined as: 4 Puk, Gandy, Wang and Park Z R 1 t − b C(a; b) = X(t)p Ψ( )dt (4) a a where Ψ is the mother wavelet, C(a; b) are the WT coefficients of the signal X(t), a is the scale parameter, and b is the shifting parameter.
Load more

Recommended publications
  • A Study of EEG Feature Complexity in Epileptic Seizure Prediction
    applied sciences Article A Study of EEG Feature Complexity in Epileptic Seizure Prediction Imene Jemal 1,2,∗, Amar Mitiche 1 and Neila Mezghani 2,3 1 INRS-Centre Énergie, Matériaux et Télécommunications, Montréal, QC H5A 1K6, Canada; [email protected] 2 Centre de Recherche LICEF, Université TÉLUQ, Montréal, QC H2S 3L4, Canada; [email protected] 3 Laboratoire LIO, Centre de Recherche du CHUM, Montréal, QC H2X 0A9, Canada * Correspondence: [email protected] Abstract: The purpose of this study is (1) to provide EEG feature complexity analysis in seizure prediction by inter-ictal and pre-ital data classification and, (2) to assess the between-subject variability of the considered features. In the past several decades, there has been a sustained interest in predicting epilepsy seizure using EEG data. Most methods classify features extracted from EEG, which they assume are characteristic of the presence of an epilepsy episode, for instance, by distinguishing a pre-ictal interval of data (which is in a given window just before the onset of a seizure) from inter-ictal (which is in preceding windows following the seizure). To evaluate the difficulty of this classification problem independently of the classification model, we investigate the complexity of an exhaustive list of 88 features using various complexity metrics, i.e., the Fisher discriminant ratio, the volume of overlap, and the individual feature efficiency. Complexity measurements on real and synthetic data testbeds reveal that that seizure prediction by pre-ictal/inter-ictal feature distinction is a problem of significant complexity. It shows that several features are clearly useful, without decidedly identifying an optimal set.
    [Show full text]
  • Computer-Aided Detection of Sleep Apnea and Sleep Stage Classification Using HRV and EEG Signals Edson F
    University of Texas at El Paso DigitalCommons@UTEP Open Access Theses & Dissertations 2010-01-01 Computer-Aided Detection Of Sleep Apnea And Sleep Stage Classification Using HRV And EEG Signals Edson F. Estrada University of Texas at El Paso, [email protected] Follow this and additional works at: https://digitalcommons.utep.edu/open_etd Part of the Biomedical Commons, Electrical and Electronics Commons, European Languages and Societies Commons, and the Scandinavian Studies Commons Recommended Citation Estrada, Edson F., "Computer-Aided Detection Of Sleep Apnea And Sleep Stage Classification Using HRV And EEG Signals" (2010). Open Access Theses & Dissertations. 2482. https://digitalcommons.utep.edu/open_etd/2482 This is brought to you for free and open access by DigitalCommons@UTEP. It has been accepted for inclusion in Open Access Theses & Dissertations by an authorized administrator of DigitalCommons@UTEP. For more information, please contact [email protected]. COMPUTER-AIDED DETECTION OF SLEEP APNEA AND SLEEP STAGE CLASSIFICATION USING HRV AND EEG SIGNALS EDSON F. ESTRADA Department of Electrical and Computer Engineering APPROVED: ___________________________________ Homer Nazeran, Ph.D., Chair ___________________________________ Patricia A. Nava, Ph.D., Co-Chair ___________________________________ Scott Starks, Ph.D. ___________________________________ Humberto Ochoa, Ph.D. ___________________________________ Luis Carcoba, Ph.D. ____________________________ Patricia D. Witherspoon, Ph.D. Dean of the Graduate School COMPUTER-AIDED DETECTION OF SLEEP APNEA AND SLEEP STAGE CLASSIFICATION USING HRV AND EEG SIGNALS By EDSON F. ESTRADA, M.S. EE DISSERTATION Presented to the Faculty of the Graduate School of The University of Texas at El Paso In Partial Fulfillment of the Requirements for the Degree of Doctor of Philosophy Department of Electrical and Computer Engineering THE UNIVERSITY OF TEXAS AT EL PASO DICEMBER 2010 Acknowledgements I would like to express my gratitude to the following people for their support and assistance in developing this dissertation.
    [Show full text]
  • Hidden Conditional Random Fields for Classification of Imaginary Motor Tasks from Eeg Data
    HIDDEN CONDITIONAL RANDOM FIELDS FOR CLASSIFICATION OF IMAGINARY MOTOR TASKS FROM EEG DATA Jaime F. Delgado Saa†‡,Mujdat¨ C¸etin† † Signal Processing and Information Systems Laboratory, Sabanci University Orhanli, Tuzla, 34956 Istanbul, Turkey ‡ Department of Electrical and Electronics Engineering, Universidad del Norte Barranquilla, Colombia [ email: delgado, mcetin ]@sabanciuniv.edu ABSTRACT the EEG signals have been proposed [4, 5, 6]. Furthermore, algo- rithms involving stochastic time series models taking into account Brain-computer interfaces (BCIs) are systems that allow the changes of the signal power with time, such as hidden Markov mod- control of external devices using information extracted from brain els (HMMs) [7, 8, 9, 10] have been used in combination with fea- signals. Such systems find application in rehabilitation of patients tures describing the temporal behavior of the EEG signals [11, 12]. with limited or no muscular control. One mechanism used in BCIs We share the perspective with this latter body of work that changes is the imagination of motor activity, which produces variations on in the power of the signals during execution of motor tasks reflect the power of the electroencephalography (EEG) signals recorded the underlying states in the brain and that the sequence of states pro- over the motor cortex. In this paper, we propose a new approach for vides useful information for discrimination of different imaginary classification of imaginary motor tasks based on hidden conditional motor tasks. In previous work based
    [Show full text]
  • A Comparative Review on Sleep Stage Classification Methods in Patients and Healthy Individuals Reza Boostani, Foroozan Karimzadeh, Mohammad Torabi-Nami
    A Comparative Review on Sleep Stage Classification Methods in Patients and healthy Individuals Reza Boostani, Foroozan Karimzadeh, Mohammad Torabi-Nami To cite this version: Reza Boostani, Foroozan Karimzadeh, Mohammad Torabi-Nami. A Comparative Review on Sleep Stage Classification Methods in Patients and healthy Individuals. 2016. hal-01390384 HAL Id: hal-01390384 https://hal.archives-ouvertes.fr/hal-01390384 Preprint submitted on 1 Nov 2016 HAL is a multi-disciplinary open access L’archive ouverte pluridisciplinaire HAL, est archive for the deposit and dissemination of sci- destinée au dépôt et à la diffusion de documents entific research documents, whether they are pub- scientifiques de niveau recherche, publiés ou non, lished or not. The documents may come from émanant des établissements d’enseignement et de teaching and research institutions in France or recherche français ou étrangers, des laboratoires abroad, or from public or private research centers. publics ou privés. A Comparative Review on Sleep Stage Classification Methods in Patients and healthy Individuals Reza Boostania, Foroozan Karimzadehb∗, Mohammad Torabi-Namic a;b Department of Computer Science and Information technology, School of Electrical and Computer Engineering, Shiraz University, Shiraz, Iran. c Department of Neuroscience, School of Advanced Medical Sciences and Technologies, Shiraz University of Medical Sciences, Shiraz, Iran. [email protected] , [email protected] ∗ Corresponding author: Tel: +987136474605, E-mail: [email protected] Abstract Background and objective: Proper scoring of sleep stages can give clinical information on diagnosing patients with sleep disor- ders. Since traditional visual scoring of the entire sleep is highly time-consuming and dependent to experts’ experience, automatic schemes based on electroencephalogram (EEG) analysis are broadly developed to solve these problems.
    [Show full text]
  • A Fast and Accurate Approach for Real-Time Seizure Detection in the Iomt
    A Fast and Accurate Approach for Real-Time Seizure Detection in the IoMT Md Abu Sayeed Saraju P. Mohanty Dept. of Computer Science and Engineering Dept. of Computer Science and Engineering University of North Texas, USA. University of North Texas, USA. Email: [email protected] Email: [email protected] Elias Kougianos Hitten Zaveri Dept. of Engineering Technology Department of Neurology University of North Texas, USA. Yale University, USA. Email: [email protected] Email: [email protected] Abstract—We propose an EEG-based seizure detection method monitoring brain function and dysfunction. In epilepsy we are which uses the discrete wavelet transform (DWT), Hjorth pa- primarily interested in two states: ictal (seizure) and interictal rameters and a k-NN classifier. Seizure detection is performed in (between seizure). Seizures can be identified by visual inspec- three stages. In the first stage, EEG signals are decomposed by the DWT into sub-bands and Hjorth parameters are extracted from tion of the EEG, though this takes considerable time and effort each of these sub-bands. In the second stage, a k-NN classifier [10]. Computer assisted detection of seizures can be valuable is used to classify the EEG data. The results demonstrate a if it can overcome these drawbacks. EEG signals can be well significant difference in Hjorth parameters between interictal and characterized from extracted features which serve to capture ictal EEG with ictal EEG being less complex than interictal EEG. distinctive information and can be central to the accuracy of We report an accuracy of 100% for a classification of normal vs.
    [Show full text]
  • Decoding the Neural Signatures of Valence and Arousal from Portable EEG Headset
    bioRxiv preprint doi: https://doi.org/10.1101/2021.07.23.453533; this version posted July 23, 2021. The copyright holder for this preprint (which was not certified by peer review) is the author/funder, who has granted bioRxiv a license to display the preprint in perpetuity. It is made available under aCC-BY 4.0 International license. Decoding the Neural Signatures of Valence and Arousal From Portable EEG Headset Nikhil Garg1,2,3,*, Rohit Garg1,3, Parrivesh NS1,3, Apoorv Anand1,3, V.A.S. Abhinav1,3, Veeky Baths1,3,* 1 Cognitive Neuroscience Lab, BITS Pilani - K.K.Birla Goa Campus, Goa, India 2 Institut Interdisciplinaire d'Innovation Technologique (3IT), Laboratoire Nanotechnologies Nanosyst`emes(LN2) { CNRS UMI-3463 { 3IT, Universit´ede Sherbrooke, Sherbrooke, Canada 3 Ironwork Insights Pvt. Ltd., India * Corresponding authors * [email protected] * [email protected] Abstract This paper focuses on classifying emotions on the valence-arousal plane using various feature extraction, feature selection and machine learning techniques. Emotion classification using EEG data and machine learning techniques has been on the rise in the recent past. We evaluate different feature extraction techniques, feature selection techniques and propose the optimal set of features and electrodes for emotion recognition. The images from the OASIS image dataset were used for eliciting the valence and arousal emotions, and the EEG data was recorded using the Emotiv Epoc X mobile EEG headset. The analysis is additionally carried out on publicly available datasets: DEAP and DREAMER. We propose a novel feature ranking technique and incremental learning approach to analyze the dependence of performance on the number of participants.
    [Show full text]
  • Arxiv:1908.00492V1 [Eess.SP] 1 Aug 2019 Review Continuous Electroencephalograms (Eegs) to Monitor Epileptic Patients
    A review of feature extraction and performance evaluation in epileptic seizure detection using EEG Poomipat Boonyakitanont1, Apiwat Lek-uthai1, Krisnachai Chomtho2, and Jitkomut Songsiri1 1Department of Electrical Engineering, Faculty of Engineering, Chulalongkorn University, Thailand 2Department of Pediatrics, Faculty of Medicine, Chulalongkorn University, Thailand August 2, 2019 Abstract Since the manual detection of electrographic seizures in continuous electroencephalogram (EEG) monitoring is very time-consuming and requires a trained expert, attempts to develop automatic seizure detection are diverse and ongoing. Machine learning approaches are intensely being applied to this problem due to their ability to classify seizure conditions from a large amount of data, and provide pre-screened results for neurologists. Several features, data trans- formations, and classifiers have been explored to analyze and classify seizures via EEG signals. In the literature, some jointly-applied features used in the classification may have shared simi- lar contributions, making them redundant in the learning process. Therefore, this paper aims to comprehensively summarize feature descriptions and their interpretations in characterizing epileptic seizures using EEG signals, as well as to review classification performance metrics. To provide meaningful information of feature selection, we conducted an experiment to examine the quality of each feature independently. The Bayesian error and non-parametric probability distribution estimation were employed to determine the significance of the individual features. Moreover, a redundancy analysis using a correlation-based feature selection was applied. The results showed that the following features {variance, energy, nonlinear energy, and Shannon entropy computed on a raw EEG signal, as well as variance, energy, kurtosis, and line length calculated on wavelet coefficients{ were able to significantly capture the seizures.
    [Show full text]
  • A MATLAB Toolkit for Computation of Multiple Measures on Time Series Data Bases
    Accepted in the Journal of Statistical Software, January 2010 Measures of Analysis of Time Series (MATS): A MATLAB Toolkit for Computation of Multiple Measures on Time Series Data Bases Dimitris Kugiumtzis, Alkiviadis Tsimpiris Department of Mathematical, Physical and Computational Sciences Faculty of Engineering, Aristotle University of Thessaloniki Thessaloniki 54124, Greece Corresponding author Dimitris Kugiumtzis Department of Mathematical, Physical and Computational Sciences, Faculty of Engineering, Aristotle University of Thessaloniki, Thessaloniki 54124, Greece e-mail: [email protected] url: http://users.auth.gr/dkugiu fax: +30 2310995958 Running title Optimal Measures and Preictal States Abstract In many applications, such as physiology and finance, large time series data bases are to be analyzed requir- ing the computation of linear, nonlinear and other measures. Such measures have been developed and imple- mented in commercial and freeware softwares rather selectively and independently. The Measures of Analysis of Time Series (MATS) MATLAB toolkit is designed to handle an arbitrary large set of scalar time series and compute a large variety of measures on them, allowing for the specification of varying measure parameters as well. The variety of options with added facilities for visualization of the results support different settings of time series analysis, such as the detection of dynamics changes in long data records, resampling (surrogate or bootstrap) tests for independence and linearity with various test statistics, and discrimination power of different measures and for different combinations of their parameters. The basic features of MATS are presented and the implemented measures are briefly described. The usefulness of MATS is illustrated on some empirical examples along with screenshots.
    [Show full text]
  • Quality Assessment of Single-Channel EEG for Wearable Devices
    sensors Article Quality Assessment of Single-Channel EEG for Wearable Devices Fanny Grosselin 1,2,* , Xavier Navarro-Sune 2 , Alessia Vozzi 2, Katerina Pandremmenou 2, Fabrizio De Vico Fallani 1,3, Yohan Attal 2 and Mario Chavez 4 1 hlSorbonne Université, UPMC Univ. Paris 06, INSERM U-1127, CNRS UMR-7225, Institut du Cerveau et de la Moelle Épinière (ICM), Groupe Hospitalier Pitié Salpêtrière-Charles Foix, 75013 Paris, France 2 myBrainTechnologies, 75010 Paris, France; [email protected] (X.N.-S.); [email protected] (A.V.); [email protected] (K.P.); [email protected] (Y.A.) 3 INRIA, Aramis Project-Team, F-75013 Paris, France; [email protected] 4 CNRS UMR-7225, Groupe Hospitalier Pitié-Salpêtrière-Charles Foix, 75013 Paris, France; [email protected] * Correspondence: [email protected] Received: 22 January 2019; Accepted: 28 January 2019; Published: 31 January 2019 Abstract: The recent embedding of electroencephalographic (EEG) electrodes in wearable devices raises the problem of the quality of the data recorded in such uncontrolled environments. These recordings are often obtained with dry single-channel EEG devices, and may be contaminated by many sources of noise which can compromise the detection and characterization of the brain state studied. In this paper, we propose a classification-based approach to effectively quantify artefact contamination in EEG segments, and discriminate muscular artefacts. The performance of our method were assessed on different databases containing either artificially contaminated or real artefacts recorded with different type of sensors, including wet and dry EEG electrodes. Furthermore, the quality of unlabelled databases was evaluated.
    [Show full text]
  • Neural Networks Time Domain Parameters As a Feature for EEG-Based Brain–Computer Interfaces
    Neural Networks 22 (2009) 1313–1319 Contents lists available at ScienceDirect Neural Networks journal homepage: www.elsevier.com/locate/neunet 2009 Special Issue Time Domain Parameters as a feature for EEG-based Brain–Computer InterfacesI Carmen Vidaurre c,a,∗, Nicole Krämer c, Benjamin Blankertz c,a, Alois Schlögl b a IDA at Fraunhofer FIRST, Kekulestr. 7, 12489 Berlin, Germany b Institute for Human–Computer Interfaces, University of Technology Graz, Krengasse 37/I, 8010 Graz, Austria c Machine Learning Group, Berlin Institute of Technology, Franklinstr. 28/29, 10587 Berlin, Germany article info a b s t r a c t Article history: Several feature types have been used with EEG-based Brain–Computer Interfaces. Among the most Received 14 October 2008 popular are logarithmic band power estimates with more or less subject-specific optimization of the Received in revised form 3 July 2009 frequency bands. In this paper we introduce a feature called Time Domain Parameter that is defined by Accepted 16 July 2009 the generalization of the Hjorth parameters. Time Domain Parameters are studied under two different conditions. The first setting is defined when no data from a subject is available. In this condition our Keywords: results show that Time Domain Parameters outperform all band power features tested with all spatial Brain–Computer Interface filters applied. The second setting is the transition from calibration (no feedback) to feedback, in which Hjorth parameters Band power estimates the frequency content of the signals can change for some subjects. We compare Time Domain Parameters Time Domain Parameters with logarithmic band power in subject-specific bands and show that these features are advantageous in Derivative operator this situation as well.
    [Show full text]
  • Predicting Exact Valence and Arousal Values from EEG
    sensors Article Predicting Exact Valence and Arousal Values from EEG Filipe Galvão, Soraia M. Alarcão and Manuel J. Fonseca * LASIGE, Faculdade de Ciências, Universidade de Lisboa, 1749-016 Lisboa, Portugal; [email protected] (F.G.); [email protected] (S.M.A.) * Correspondence: [email protected] Abstract: Recognition of emotions from physiological signals, and in particular from electroen- cephalography (EEG), is a field within affective computing gaining increasing relevance. Although researchers have used these signals to recognize emotions, most of them only identify a limited set of emotional states (e.g., happiness, sadness, anger, etc.) and have not attempted to predict exact values for valence and arousal, which would provide a wider range of emotional states. This paper describes our proposed model for predicting the exact values of valence and arousal in a subject-independent scenario. To create it, we studied the best features, brain waves, and machine learning models that are currently in use for emotion classification. This systematic analysis revealed that the best prediction model uses a KNN regressor (K = 1) with Manhattan distance, features from the alpha, beta and gamma bands, and the differential asymmetry from the alpha band. Results, using the DEAP, AMIGOS and DREAMER datasets, show that our model can predict valence and arousal values with a low error (MAE < 0.06, RMSE < 0.16) and a strong correlation between predicted and expected values (PCC > 0.80), and can identify four emotional classes with an accuracy of 84.4%. The findings of this work show that the features, brain waves and machine learning models, typically used in emotion classification tasks, can be used in more challenging situations, such as the prediction of exact values for valence and arousal.
    [Show full text]
  • Epileptic Seizure Detection Using Deep Ensemble Network with Empirical Wavelet Transform
    MEASUREMENT SCIENCE REVIEW, 21, (2021), No. 4, 110-116 Journal homepage: https://content.sciendo.com Epileptic Seizure Detection using Deep Ensemble Network with Empirical Wavelet Transform Sreelekha Panda1, Abhishek Das2, Satyasis Mishra1, Mihir Narayan Mohanty2* 1Dept. Of ECE, Centurion University of Technology and Management, Odisha, India 2Dept. Of ECE, ITER, Siksha ‘O’ Anusandhan (Deemed to be University), Bhubaneswar, Odisha, India [email protected] Epileptic seizure attack is caused by abnormal brain activity of human subjects. Certain cases will lead to death. The detection and diagnosis is therefore an important task. It can be performed either by direct patient activity during seizure or by electroencephalogram (EEG) signal analysis by neurologists. EEG signal processing and detection of seizures using machine learning techniques make this task easier than manual detection. To overcome this problem related to a neurological disorder, we have proposed the ensemble learning technique for improved detection of epilepsy seizures from EEG signals. In the first stage, EEG signal decomposition is done by utilizing empirical wavelet transform (EWT) for smooth analysis in terms of sub-bands. Further, features are extracted from each sub. Time and frequency domain features are the two categories used to extract the statistical features. These features are used in a stacked ensemble of deep neural network (DNN) model along with multilayer Perceptron (MLP) for the detection and classification of ictal, inter-ictal, and pre-ictal (normal) signals. The proposed method is verified using two publicly available datasets provided by the University of Bonn (UoB dataset) and Neurology and Sleep Center - New Delhi (NSC-ND dataset).
    [Show full text]